Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
[edit]
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:59325940, 2018.
Abstract
Variance reduction has been commonly used in stochastic optimization. It relies crucially on the assumption that the data set is finite. However, when the data are imputed with random noise as in data augmentation, the perturbed data set becomes essentially infinite. Recently, the stochastic MISO (SMISO) algorithm is introduced to address this expected risk minimization problem. Though it converges faster than SGD, a significant amount of memory is required. In this paper, we propose two SGDlike algorithms for expected risk minimization with random perturbation, namely, stochastic sample average gradient (SSAG) and stochastic SAGA (SSAGA). The memory cost of SSAG does not depend on the sample size, while that of SSAGA is the same as those of variance reduction methods on unperturbed data. Theoretical analysis and experimental results on logistic regression and AUC maximization show that SSAG has faster convergence rate than SGD with comparable space requirement while SSAGA outperforms SMISO in terms of both iteration complexity and storage.
Related Material


